selftestcrawljobhandler.html
来自「网络爬虫开源代码」· HTML 代码 · 共 438 行 · 第 1/2 页
HTML
438 行
<TD><CODE><A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#addJob(org.archive.crawler.admin.CrawlJob)">addJob</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#addProfile(org.archive.crawler.admin.CrawlJob)">addProfile</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#checkDirectory(java.io.File)">checkDirectory</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#checkpointJob()">checkpointJob</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#crawlCheckpoint(java.io.File)">crawlCheckpoint</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#crawlEnding(java.lang.String)">crawlEnding</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#crawlPaused(java.lang.String)">crawlPaused</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#crawlPausing(java.lang.String)">crawlPausing</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#crawlResuming(java.lang.String)">crawlResuming</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#createNewJob(java.io.File, java.lang.String, java.lang.String, java.lang.String, int)">createNewJob</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#createSettingsHandler(java.io.File, java.lang.String, java.lang.String, java.lang.String, java.io.File, org.archive.crawler.admin.CrawlJobErrorHandler, java.lang.String, java.lang.String)">createSettingsHandler</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#deleteJob(java.lang.String)">deleteJob</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#deleteProfile(org.archive.crawler.admin.CrawlJob)">deleteProfile</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#deleteURIsFromPending(java.lang.String)">deleteURIsFromPending</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#discardNewJob()">discardNewJob</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#doFlush()">doFlush</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#ensureNewJobWritten(org.archive.crawler.admin.CrawlJob, java.lang.String, java.lang.String)">ensureNewJobWritten</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#getCompletedJobs()">getCompletedJobs</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#getCurrentJob()">getCurrentJob</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#getDefaultProfile()">getDefaultProfile</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#getInitialMarker(java.lang.String, boolean)">getInitialMarker</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#getJob(java.lang.String)">getJob</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#getNewJob()">getNewJob</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#getNextJobUID()">getNextJobUID</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#getPendingJobs()">getPendingJobs</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#getPendingURIsList(org.archive.crawler.framework.FrontierMarker, int, boolean)">getPendingURIsList</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#getProfiles()">getProfiles</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#getStateJobFile(java.io.File)">getStateJobFile</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#importUri(java.lang.String, boolean, boolean)">importUri</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#importUri(java.lang.String, boolean, boolean, boolean)">importUri</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#importUris(java.io.InputStream, java.lang.String, boolean)">importUris</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#importUris(java.lang.String, java.lang.String, boolean)">importUris</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#importUris(java.lang.String, java.lang.String, java.lang.String)">importUris</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#isCrawling()">isCrawling</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#isRunning()">isRunning</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#kickUpdate()">kickUpdate</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#loadJob(java.io.File)">loadJob</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#loadOptions(java.lang.String)">loadOptions</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#loadProfile(java.io.File)">loadProfile</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#newJob(org.archive.crawler.admin.CrawlJob, java.lang.String, java.lang.String, java.lang.String, java.lang.String, int)">newJob</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#newJob(java.io.File, java.lang.String, java.lang.String, java.lang.String)">newJob</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#newProfile(org.archive.crawler.admin.CrawlJob, java.lang.String, java.lang.String, java.lang.String)">newProfile</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#pauseJob()">pauseJob</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#requestCrawlStop()">requestCrawlStop</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#resumeJob()">resumeJob</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#setDefaultProfile(org.archive.crawler.admin.CrawlJob)">setDefaultProfile</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#startCrawler()">startCrawler</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#startNextJob()">startNextJob</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#startNextJobInternal()">startNextJobInternal</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#stop()">stop</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#stopCrawler()">stopCrawler</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#terminateCurrentJob()">terminateCurrentJob</A>, <A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#updateRecoveryPaths(java.io.File, org.archive.crawler.settings.SettingsHandler, java.lang.String)">updateRecoveryPaths</A></CODE></TD></TR></TABLE> <A NAME="methods_inherited_from_class_java.lang.Object"><!-- --></A><TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY=""><TR BGCOLOR="#EEEEFF" CLASS="TableSubHeadingColor"><TH ALIGN="left"><B>Methods inherited from class java.lang.Object</B></TH></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD><CODE>clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait</CODE></TD></TR></TABLE> <P><!-- ========= CONSTRUCTOR DETAIL ======== --><A NAME="constructor_detail"><!-- --></A><TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY=""><TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor"><TH ALIGN="left" COLSPAN="1"><FONT SIZE="+2"><B>Constructor Detail</B></FONT></TH></TR></TABLE><A NAME="SelfTestCrawlJobHandler(java.io.File, java.lang.String, java.lang.String)"><!-- --></A><H3>SelfTestCrawlJobHandler</H3><PRE>public <B>SelfTestCrawlJobHandler</B>(java.io.File jobsDir, java.lang.String selfTestName, java.lang.String url)</PRE><DL></DL><!-- ============ METHOD DETAIL ========== --><A NAME="method_detail"><!-- --></A><TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY=""><TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor"><TH ALIGN="left" COLSPAN="1"><FONT SIZE="+2"><B>Method Detail</B></FONT></TH></TR></TABLE><A NAME="crawlStarted(java.lang.String)"><!-- --></A><H3>crawlStarted</H3><PRE>public void <B>crawlStarted</B>(java.lang.String message)</PRE><DL><DD><B>Description copied from interface: <CODE><A HREF="../../../../org/archive/crawler/event/CrawlStatusListener.html#crawlStarted(java.lang.String)">CrawlStatusListener</A></CODE></B></DD><DD>Called on crawl start.<P><DD><DL><DT><B>Specified by:</B><DD><CODE><A HREF="../../../../org/archive/crawler/event/CrawlStatusListener.html#crawlStarted(java.lang.String)">crawlStarted</A></CODE> in interface <CODE><A HREF="../../../../org/archive/crawler/event/CrawlStatusListener.html" title="interface in org.archive.crawler.event">CrawlStatusListener</A></CODE><DT><B>Overrides:</B><DD><CODE><A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#crawlStarted(java.lang.String)">crawlStarted</A></CODE> in class <CODE><A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html" title="class in org.archive.crawler.admin">CrawlJobHandler</A></CODE></DL></DD><DD><DL><DT><B>Parameters:</B><DD><CODE>message</CODE> - Start message.</DL></DD></DL><HR><A NAME="crawlEnded(java.lang.String)"><!-- --></A><H3>crawlEnded</H3><PRE>public void <B>crawlEnded</B>(java.lang.String sExitMessage)</PRE><DL><DD><B>Description copied from interface: <CODE><A HREF="../../../../org/archive/crawler/event/CrawlStatusListener.html#crawlEnded(java.lang.String)">CrawlStatusListener</A></CODE></B></DD><DD>Called when a CrawlController has ended a crawl and is about to exit.<P><DD><DL><DT><B>Specified by:</B><DD><CODE><A HREF="../../../../org/archive/crawler/event/CrawlStatusListener.html#crawlEnded(java.lang.String)">crawlEnded</A></CODE> in interface <CODE><A HREF="../../../../org/archive/crawler/event/CrawlStatusListener.html" title="interface in org.archive.crawler.event">CrawlStatusListener</A></CODE><DT><B>Overrides:</B><DD><CODE><A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html#crawlEnded(java.lang.String)">crawlEnded</A></CODE> in class <CODE><A HREF="../../../../org/archive/crawler/admin/CrawlJobHandler.html" title="class in org.archive.crawler.admin">CrawlJobHandler</A></CODE></DL></DD><DD><DL><DT><B>Parameters:</B><DD><CODE>sExitMessage</CODE> - Type of exit. Should be one of the STATUS constants in defined in CrawlJob.<DT><B>See Also:</B><DD><A HREF="../../../../org/archive/crawler/admin/CrawlJob.html" title="class in org.archive.crawler.admin"><CODE>CrawlJob</CODE></A></DL></DD></DL><HR><A NAME="crawledURIDisregard(org.archive.crawler.datamodel.CrawlURI)"><!-- --></A><H3>crawledURIDisregard</H3><PRE>public void <B>crawledURIDisregard</B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A> curi)</PRE><DL><DD><B>Description copied from interface: <CODE><A HREF="../../../../org/archive/crawler/event/CrawlURIDispositionListener.html#crawledURIDisregard(org.archive.crawler.datamodel.CrawlURI)">CrawlURIDispositionListener</A></CODE></B></DD><DD>Notification of a crawled URI that is to be disregarded. Usually this means that the robots.txt file for the relevant site forbids this from being crawled and we are therefor not going to keep it. Other reasons may apply. In all cases this means that it <i>was</i> successfully downloaded but will not be stored.<P><DD><DL><DT><B>Specified by:</B><DD><CODE><A HREF="../../../../org/archive/crawler/event/CrawlURIDispositionListener.html#crawledURIDisregard(org.archive.crawler.datamodel.CrawlURI)">crawledURIDisregard</A></CODE> in interface <CODE><A HREF="../../../../org/archive/crawler/event/CrawlURIDispositionListener.html" title="interface in org.archive.crawler.event">CrawlURIDispositionListener</A></CODE></DL></DD><DD><DL><DT><B>Parameters:</B><DD><CODE>curi</CODE> - The relevant CrawlURI</DL></DD></DL><HR><A NAME="crawledURIFailure(org.archive.crawler.datamodel.CrawlURI)"><!-- --></A><H3>crawledURIFailure</H3><PRE>public void <B>crawledURIFailure</B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A> curi)</PRE><DL><DD><B>Description copied from interface: <CODE><A HREF="../../../../org/archive/crawler/event/CrawlURIDispositionListener.html#crawledURIFailure(org.archive.crawler.datamodel.CrawlURI)">CrawlURIDispositionListener</A></CODE></B></DD><DD>Notification of a failed crawling of a URI. The failure is of a type that precludes retries (either by it's very nature or because it has been retried to many times)<P><DD><DL><DT><B>Specified by:</B><DD><CODE><A HREF="../../../../org/archive/crawler/event/CrawlURIDispositionListener.html#crawledURIFailure(org.archive.crawler.datamodel.CrawlURI)">crawledURIFailure</A></CODE> in interface <CODE><A HREF="../../../../org/archive/crawler/event/CrawlURIDispositionListener.html" title="interface in org.archive.crawler.event">CrawlURIDispositionListener</A></CODE></DL></DD><DD><DL><DT><B>Parameters:</B><DD><CODE>curi</CODE> - The relevant CrawlURI</DL></DD></DL><HR><A NAME="crawledURINeedRetry(org.archive.crawler.datamodel.CrawlURI)"><!-- --></A><H3>crawledURINeedRetry</H3><PRE>public void <B>crawledURINeedRetry</B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A> curi)</PRE><DL><DD><B>Description copied from interface: <CODE><A HREF="../../../../org/archive/crawler/event/CrawlURIDispositionListener.html#crawledURINeedRetry(org.archive.crawler.datamodel.CrawlURI)">CrawlURIDispositionListener</A></CODE></B></DD><DD>Notification of a failed crawl of a URI that will be retried (failure due to possible transient problems).<P><DD><DL><DT><B>Specified by:</B><DD><CODE><A HREF="../../../../org/archive/crawler/event/CrawlURIDispositionListener.html#crawledURINeedRetry(org.archive.crawler.datamodel.CrawlURI)">crawledURINeedRetry</A></CODE> in interface <CODE><A HREF="../../../../org/archive/crawler/event/CrawlURIDispositionListener.html" title="interface in org.archive.crawler.event">CrawlURIDispositionListener</A></CODE></DL></DD><DD><DL><DT><B>Parameters:</B><DD><CODE>curi</CODE> - The relevant CrawlURI</DL></DD></DL><HR><A NAME="crawledURISuccessful(org.archive.crawler.datamodel.CrawlURI)"><!-- --></A><H3>crawledURISuccessful</H3><PRE>public void <B>crawledURISuccessful</B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A> curi)</PRE><DL><DD><B>Description copied from interface: <CODE><A HREF="../../../../org/archive/crawler/event/CrawlURIDispositionListener.html#crawledURISuccessful(org.archive.crawler.datamodel.CrawlURI)">CrawlURIDispositionListener</A></CODE></B></DD><DD>Notification of a successfully crawled URI<P><DD><DL><DT><B>Specified by:</B><DD><CODE><A HREF="../../../../org/archive/crawler/event/CrawlURIDispositionListener.html#crawledURISuccessful(org.archive.crawler.datamodel.CrawlURI)">crawledURISuccessful</A></CODE> in interface <CODE><A HREF="../../../../org/archive/crawler/event/CrawlURIDispositionListener.html" title="interface in org.archive.crawler.event">CrawlURIDispositionListener</A></CODE></DL></DD><DD><DL><DT><B>Parameters:</B><DD><CODE>curi</CODE> - The relevant CrawlURI</DL></DD></DL><!-- ========= END OF CLASS DATA ========= --><HR><!-- ======= START OF BOTTOM NAVBAR ====== --><A NAME="navbar_bottom"><!-- --></A><A HREF="#skip-navbar_bottom" title="Skip navigation links"></A><TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0" SUMMARY=""><TR><TD COLSPAN=2 BGCOLOR="#EEEEFF" CLASS="NavBarCell1"><A NAME="navbar_bottom_firstrow"><!-- --></A><TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3" SUMMARY=""> <TR ALIGN="center" VALIGN="top"> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A> </TD> <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> <FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="class-use/SelfTestCrawlJobHandler.html"><FONT CLASS="NavBarFont1"><B>Use</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../index-all.html"><FONT CLASS="NavBarFont1"><B>Index</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A> </TD> </TR></TABLE></TD><TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM></EM></TD></TR><TR><TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2"> <A HREF="../../../../org/archive/crawler/selftest/SelfTestCase.html" title="class in org.archive.crawler.selftest"><B>PREV CLASS</B></A> NEXT CLASS</FONT></TD><TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2"> <A HREF="../../../../index.html?org/archive/crawler/selftest/SelfTestCrawlJobHandler.html" target="_top"><B>FRAMES</B></A> <A HREF="SelfTestCrawlJobHandler.html" target="_top"><B>NO FRAMES</B></A> <SCRIPT type="text/javascript"> <!-- if(window==top) { document.writeln('<A HREF="../../../../allclasses-noframe.html"><B>All Classes</B></A>'); } //--></SCRIPT><NOSCRIPT> <A HREF="../../../../allclasses-noframe.html"><B>All Classes</B></A></NOSCRIPT></FONT></TD></TR><TR><TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2"> SUMMARY: NESTED | <A HREF="#fields_inherited_from_class_org.archive.crawler.admin.CrawlJobHandler">FIELD</A> | <A HREF="#constructor_summary">CONSTR</A> | <A HREF="#method_summary">METHOD</A></FONT></TD><TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">DETAIL: FIELD | <A HREF="#constructor_detail">CONSTR</A> | <A HREF="#method_detail">METHOD</A></FONT></TD></TR></TABLE><A NAME="skip-navbar_bottom"></A><!-- ======== END OF BOTTOM NAVBAR ======= --><HR>Copyright © 2003-2007 Internet Archive. All Rights Reserved.</BODY></HTML>
⌨️ 快捷键说明
复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?